mm: change huge_ptep_clear_flush() to return the original pte

Patch series "Fix CONT-PTE/PMD size hugetlb issue when unmapping or migrating", v4.

presently, migrating a hugetlb page or unmapping a poisoned hugetlb page,
we'll use ptep_clear_flush() and set_pte_at() to nuke the page table entry
and remap it, and this is incorrect for CONT-PTE or CONT-PMD size hugetlb
page, which will cause potential data consistent issue. This patch set
will change to use hugetlb related APIs to fix this issue.

Note: Mike pointed out the huge_ptep_get() will only return the one
specific value, and it would not take into account the dirty or young bits
of CONT-PTE/PMDs like the huge_ptep_get_and_clear() [1]. This
inconsistent issue is not introduced by this patch set, and this issue
will be addressed in another thread [2]. Meanwhile the uffd for hugetlb
case [3] pointed out by Gerald also needs another patch to address.

[1] https://lore.kernel.org/linux-mm/[e-mail]/
[2] https://lore.kernel.org/all/[e-mail]/
[3] https://lore.kernel.org/linux-mm/20220503120343.6264e126@thinkpad/


This patch (of 3):

It is incorrect to use ptep_clear_flush() to nuke a hugetlb page table
when unmapping or migrating a hugetlb page, and will change to use
huge_ptep_clear_flush() instead in the following patches.

So this is a preparation patch, which changes the huge_ptep_clear_flush()
to return the original pte to help to nuke a hugetlb page table.

[[e-mail]: fix build in several more architectures]
Link: https://lkml.kernel.org/r/[e-mail]
[[e-mail]: fixup]
Link: https://lkml.kernel.org/r/[e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Link: https://lkml.kernel.org/r/20f[e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Link: https://lkml.kernel.org/r/dcf[e-mail]
Signed-off-by: Baolin Wang <[e-mail]>
Signed-off-by: Stephen Rothwell <[e-mail]>
Acked-by: Mike Kravetz <[e-mail]>
Reviewed-by: Muchun Song <[e-mail]>
Cc: Catalin Marinas <[e-mail]>
Cc: Will Deacon <[e-mail]>
Cc: Thomas Bogendoerfer <[e-mail]>
Cc: James Bottomley <[e-mail]>
Cc: Helge Deller <[e-mail]>
Cc: Michael Ellerman <[e-mail]>
Cc: Benjamin Herrenschmidt <[e-mail]>
Cc: Paul Mackerras <[e-mail]>
Cc: Heiko Carstens <[e-mail]>
Cc: Vasily Gorbik <[e-mail]>
Cc: Alexander Gordeev <[e-mail]>
Cc: Christian Borntraeger <[e-mail]>
Cc: Sven Schnelle <[e-mail]>
Cc: Yoshinori Sato <[e-mail]>
Cc: Rich Felker <[e-mail]>
Cc: David S. Miller <[e-mail]>
Cc: Arnd Bergmann <[e-mail]>
Cc: Gerald Schaefer <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

arch/arm64/include/asm/hugetlb.h

···
 extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep);
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
-				  unsigned long addr, pte_t *ptep);
+extern pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+				   unsigned long addr, pte_t *ptep);
 #define __HAVE_ARCH_HUGE_PTE_CLEAR
 extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep, unsigned long sz);

arch/arm64/mm/hugetlbpage.c

···
 		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
 }
 
-void huge_ptep_clear_flush(struct vm_area_struct *vma,
-			   unsigned long addr, pte_t *ptep)
+pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+			    unsigned long addr, pte_t *ptep)
 {
 	size_t pgsize;
 	int ncontig;
 
-	if (!pte_cont(READ_ONCE(*ptep))) {
-		ptep_clear_flush(vma, addr, ptep);
-		return;
-	}
+	if (!pte_cont(READ_ONCE(*ptep)))
+		return ptep_clear_flush(vma, addr, ptep);
 
 	ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
-	clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
+	return get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
 }
 
 static int __init hugetlbpage_init(void)

arch/ia64/include/asm/hugetlb.h

···
 #define is_hugepage_only_range is_hugepage_only_range
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep)
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+					  unsigned long addr, pte_t *ptep)
 {
+	return *ptep;
 }
 
 #include <asm-generic/hugetlb.h>

arch/mips/include/asm/hugetlb.h

···
 }
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep)
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+					  unsigned long addr, pte_t *ptep)
 {
+	pte_t pte;
+
 	/*
 	 * clear the huge pte entry firstly, so that the other smp threads will
 	 * not get old pte entry after finishing flush_tlb_page and before
 	 * setting new huge pte entry
 	 */
-	huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
 	flush_tlb_page(vma, addr);
+	return pte;
 }
 
 #define __HAVE_ARCH_HUGE_PTE_NONE

arch/parisc/include/asm/hugetlb.h

···
 }
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep)
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+					  unsigned long addr, pte_t *ptep)
 {
+	return *ptep;
 }
 
 #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT

arch/powerpc/include/asm/hugetlb.h

···
 }
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep)
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+					  unsigned long addr, pte_t *ptep)
 {
-	huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte_t pte;
+
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
 	flush_hugetlb_page(vma, addr);
+	return pte;
 }
 
 #define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS

arch/s390/include/asm/hugetlb.h

···
 		set_pte(ptep, __pte(_SEGMENT_ENTRY_EMPTY));
 }
 
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long address, pte_t *ptep)
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+					  unsigned long address, pte_t *ptep)
 {
-	huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
+	return huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
 }
 
 static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,

arch/sh/include/asm/hugetlb.h

···
 }
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep)
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+					  unsigned long addr, pte_t *ptep)
 {
+	return *ptep;
 }
 
 static inline void arch_clear_hugepage_flags(struct page *page)

arch/sparc/include/asm/hugetlb.h

···
 			      pte_t *ptep);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep)
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+					  unsigned long addr, pte_t *ptep)
 {
+	return *ptep;
 }
 
 #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT

include/asm-generic/hugetlb.h

···
 #endif
 
 #ifndef __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 		unsigned long addr, pte_t *ptep)
 {
-	ptep_clear_flush(vma, addr, ptep);
+	return ptep_clear_flush(vma, addr, ptep);
 }
 #endif